Claim Missing Document
Check
Articles

Found 7 Documents
Search

Improved feature extraction method and K-means clustering for soil fertility identification based on soil image Ramadhanu, Agung; Hendri, Halifia; Enggari, Sofika; Andini, Silfia; Devita, Retno; Rianti, Eva
Indonesian Journal of Electrical Engineering and Computer Science Vol 38, No 3: June 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v38.i3.pp2001-2011

Abstract

This research is conducting analysis of digital land images using digital image processing techniques. The main purpose of the research is to classify soil fertility based on two-dimensional RGB colored digital soil images. The research is done by extracting features and shapes from the soil image. The research uses methods of segmentation, extraction, and identification against digital soil images. This research is carried out in three stages. The first phase of this research is image pre-processing which begins with the conversion of RGB color image to Grayscale then color conversion to binary which subsequently performs noise reduction with the method Three-layer median filter. The second stage is a process that is divided into the first two stages, namely the process of segmentation by grouping RGB color images into L*a*b which is continued by clustering using the K-means clustering method. The second is the extraction of characteristics of the soil image which is characteristic of shape and texture. The final stage is the identification of soil images that are clustered into two types: fertile soils and unfertile soil. The study achieved an accuracy of 85% which could accurately identify 20 images while inaccurately classifying 5 images out of a total of 25 input images.
Evaluation of New Employee Selection using the Multi Factor Evaluation Process Method Marissa, Dian; Enggari, Sofika; Guswandi, Dodi
Journal of Computer Scine and Information Technology Volume 10 Issue 1 (2024): JCSITech
Publisher : Universitas Putra Indonesia YPTK Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35134/jcsitech.v10i1.96

Abstract

The process of accepting and selecting prospective employees is the earliest process for a company to get quality employees that the company or agency needs. Companies must have criteria for the employees they want. On CV. Adtuil Photocopying in recruiting employees is still less efficient, namely prospective employees still send application files to the company or via expedition delivery. So HRD will have difficulty in selecting prospective employees because they have to record and double-check incoming application files as well as the process of determining the right criteria . Solutions used to overcome problems on CV. Adtuil uses a decision support system for selecting new employees, using the Multi Factor Evaluation Process (MFEP) method. This method is quantitative which uses a weighting system in decision making. Application design using the Vb programming language. Net and MySQL databases that can manage data quickly and accurately. The results of this research show that there were 3 employees who received 10 alternative data, namely A1, A5, A9 with scores > 75. After using this decision support system it can help CV. Adtuil Photocopy in determining employee acceptance precisely, quickly and accurately
Implementation of the Topsis and AHP Methods in the Decision Support System for Determining the Best Employees Putri, Yolan Ananda; Sumijan; Enggari, Sofika
Journal of Computer Scine and Information Technology Volume 10 Issue 2 (2024): JCSITech
Publisher : Universitas Putra Indonesia YPTK Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35134/jcsitech.v10i2.103

Abstract

Every company or agency needs Human Resources (HR) in the form of employees who have competence and good performance. Employees are one of the most important assets owned by a company. The West Sumatra Province Transportation Service is the organizer of government affairs in the field of transportation or transportation policy for the West Sumatra Province region where the selection of the best employees is still not optimal using Microsoft Excel. The aim of designing a new system at the Provincial Transportation Service is to create optimization in the assessment of each employee to facilitate the recapitulation of employee data. The data is analyzed and processed according to the research framework, namely using a Decision Support System, especially the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) and Analytic Hierarchy Process (AHP) methods. In this research, 10 alternative employees were taken to be assessed. Based on formula calculations using the AHP method, it is used to determine the weighted value of each existing criterion, then the resulting values from the weighting are used to carry out rankings using the TOPSIS method. After carrying out calculations using these 2 methods, the result was that the best employee was alternative 9 in the name of Rusdi with a value of 0.9995. So with this calculation the results can show which employees have the right to be the best employees in that agency
Optimization of Shape, Texture, and Color Extraction Methods in Concrete Strength Detection Ramadhanu, Agung; Hendri, Hallifia; Majid, Mazlina Abdul; Enggari, Sofika; Andini, Silfia; Hidayat, Rahmad
JOIV : International Journal on Informatics Visualization Vol 9, No 6 (2025)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.9.6.4164

Abstract

The growing demand for an accurate and rapid method to assess concrete strength has driven the development of non-destructive and cost-effective techniques. This paper aims to enhance the process of extracting shape, texture, and color features from concrete surface images to improve the accuracy of strength classification through digital image processing and artificial intelligence (AI). The study uses a dataset of 300 high-resolution photographs of concrete samples, categorized by their compressive strength levels: weak, moderate, and strong. These images were taken under controlled background and lighting conditions to ensure consistency. The methodology involves three stages: image preprocessing, feature extraction, and classification. During preprocessing, RGB images are converted to the Lab color space, and a three-layer median filter is applied to reduce noise. The K-Means clustering algorithm segments the images, and relevant features such as Metric, Eccentricity, Contrast, Correlation, Energy, Homogeneity, Hue, and Saturation are extracted. Among these, Correlation and Energy are the most influential in classification accuracy. The experimental results show that the proposed approach can reach up to 90 percent accuracy in classifying concrete strength into three categories. This suggests that visual features have strong potential to replace traditional destructive testing methods. The findings also point to the possibility of enhancing prediction accuracy with deep learning models and developing real-time, field-based evaluation tools to aid quality control in the construction industry.
Automated Pixel-Level Concrete Defect Detection using U-Net Architecture: A Comparative Study with Clustering-Based Segmentation Hendri, Halifia; Rani, Larissa Navia; Enggari, Sofika; Ramadhanu, Agung; Hadi, Febri
Journal of Applied Data Sciences Vol 7, No 2: May 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i2.1298

Abstract

Concrete surface defect detection is a critical aspect of maintaining the integrity and safety of infrastructure in civil engineering. Traditional manual inspection methods are time-consuming, prone to human subjectivity, and often limited by physical accessibility, necessitating the development of robust automated solutions. This paper presents an automated pixel-level concrete surface defect detection system utilizing the U-Net deep learning architecture. The primary contribution and novelty of our approach lie in optimizing the network's encoder-decoder structure with skip connections to effectively capture both broad contextual features and precise spatial localization. This overcomes the critical limitations of existing traditional methods, which frequently struggle with complex concrete background textures, inherent noise, and uneven illumination. To validate our approach, the proposed U-Net model is systematically compared against a widely used baseline method, K-Means clustering combined with Gray-Level Co-occurrence Matrix (GLCM) texture analysis. The evaluation was conducted using a comprehensive dataset consisting of 1000 high-resolution concrete images. Experimental results reveal that the deep learning architecture vastly outperforms the traditional baseline. Specifically, the U-Net model achieved an outstanding F1-Score of 92.47%, a precision of 93.18%, and a mean Intersection over Union (mIoU) of 86.55%. In stark contrast, the K-Means and GLCM approach only yielded an F1-Score of 69.83% and an mIoU of 54.21%. These quantitative findings demonstrate that the proposed U-Net-based system not only successfully minimizes false segmentations but also provides a highly reliable, efficient, and scalable computational framework. Ultimately, this research delivers a practical solution that can be seamlessly integrated into continuous automated structural health monitoring systems, paving the way for safer and more proactive civil infrastructure management.
Implementation of Certainty Factor in an Expert System for Diagnosing Pests and Diseases of Tomato Plants Fadli, Hafizul; Enggari, Sofika; Rahman, Sepsa Nur
Journal of Computer Scine and Information Technology Volume 9 Issue 3 (2023): JCSITech
Publisher : Universitas Putra Indonesia YPTK Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35134/jcsitech.v9i3.76

Abstract

Tomatoes are a plant that is currently widely planted by farmers. Environmental factors and stable selling power are the reasons why this plant is popular with Indonesian farmers. However, that doesn't mean tomato plants don't have growth problems. Diseases such as leaf rot, fusarium wilt, bacterial wilt and leaf scorch are still the main factors inhibiting the decline in yield and quality of tomato plants in Indonesia. This is because farmers do not understand the correct diagnosis of tomato diseases. Misdiagnosis of diseases causes the use of pesticides that are not appropriate, resulting in damage or failure of tomato plants. When diagnosing tomato diseases, you need a farm advisor who can accurately diagnose tomato diseases. In this study, an expert system for diagnosing tomato plant diseases was built to determine pest and disease diagnoses and provide solutions and suggestions for existing diseases based on the selected symptoms. The method used in this expert system is certainty factor. This method was chosen because the certainty factor measures the value of a hypothesis's belief in a fact. These values are divided into two parts, namely MB and MD. The results of applying the confidence factor method to an expert system for diagnosing tomato plant diseases with examples of cases of late blight diagnosis by selecting the appropriate symptoms obtained a percentage of 97%, so it can be interpreted that the use of this method has the opportunity to solve problems in tomato plants
Poor Family Classification Decision Support System using the Simple Additive Weighting (SAW) Method Patriani, Lili Amareza; Sumijan; Enggari, Sofika
Journal of Computer Scine and Information Technology Volume 9 Issue 3 (2023): JCSITech
Publisher : Universitas Putra Indonesia YPTK Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35134/jcsitech.v9i3.83

Abstract

Poverty is a problem that continues to be the focus of attention for the government. Poverty has also caused people to be willing to sacrifice anything for their survival. To anticipate this problem, various policies have been adopted by the government to break the chain of poverty. One of them is providing assistance funds to poor families (PKH). This is felt directly by all levels of underprivileged society. One of the efforts of the Koto Ranah Tapan government to eradicate poverty that occurs in Koto Ranah Tapan is to follow the central government program, namely the launch of government financial assistance (PKH). These funds will be distributed to poor residents in Koto Ranah Tapan through the nagari guardian office in Koto Ranah Tapan. However, the distribution of aid funds to poor families is often not on target due to a large level of manual calculation error which makes the aid not on target and also the office of the nagari village of high cliff village has not been able to objectively determine the families who receive the aid. To help determine which families are worthy of receiving poor family assistance funds, a decision support system is needed. With this Decision Support System (DSS), it is hoped that the decision-making process can minimize the occurrence of wrong targets that often arise in the process of selecting poor families who wish to receive aid funds . In this calculation the author uses the Simple Additive Weighting (SAW) method, because this method is suitable for accurate calculations and is very helpful in calculating any data obtained. The results obtained were that Ade Irma Suryani got the highest score with a score of 10.8 and was ranked at the top (Best 1), so she could be considered the best recipient of aid funds.